© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1278
    Prev
    Next
    INDEX
    Explanations

    first person pronouns in the past tense

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kept
    -0.84
    kept
    -0.82
     never
    -0.81
    今後も
    -0.79
     always
    -0.76
     nigdy
    -0.75
    keep
    -0.73
     maintained
    -0.72
     Kept
    -0.72
     continue
    -0.71
    POSITIVE LOGITS
     arrives
    0.98
     arrived
    0.96
     arrival
    0.94
     begins
    0.93
     arrive
    0.92
     commences
    0.92
     begin
    0.90
     enters
    0.88
     began
    0.87
     begun
    0.85
    Activations Density 1.725%

    No Known Activations